Shadowgraph
About
Sign in

hazyresearch/my-awesome-model

Model

Based model but uses layernorm instead of QK.sum(-1) for the normalization, for better hardware efficiency.

2

stars

6

commits

1

linked in READMEs

Oct 18, 2024

updated

gpt2
pytorch

README

Based model but uses layernorm instead of QK.sum(-1) for the normalization, for better hardware efficiency.

Contributors

simarora

6 commits

Similar repos

ylwt/PaddlePaddle-gpt2

Model

0

zhouzhen6246/LIRA

Model

0

ylwt/PaddlePaddle-gpt-neo-125m

Model

0

Tongjilibo/gpt2-ml_30g_corpus

Model

0

jingqun/textharmony

Model

1

Tongjilibo/gpt2-ml_15g_corpus

Model

0

CognitiveKernel/ck-70b-v1

Model

0

binxia/LLMGA-pretrained-mlp

Model

0

Linked in READMEs

HazyResearch/ThunderKittens

Tile primitives for speedy kernels

3,674

README badge

hazyresearch/my-awesome-model

Model

Based model but uses layernorm instead of QK.sum(-1) for the normalization, for better hardware efficiency.

2

stars

6

commits

1

linked in READMEs

Oct 18, 2024

updated

gpt2
pytorch

README

Based model but uses layernorm instead of QK.sum(-1) for the normalization, for better hardware efficiency.

Similar repos

ylwt/PaddlePaddle-gpt2

Model

0

zhouzhen6246/LIRA

Model

0

ylwt/PaddlePaddle-gpt-neo-125m

Model

0

Tongjilibo/gpt2-ml_30g_corpus

Model

0

jingqun/textharmony

Model

1

Tongjilibo/gpt2-ml_15g_corpus

Model

0

CognitiveKernel/ck-70b-v1

Model

0

binxia/LLMGA-pretrained-mlp

Model

0

Linked in READMEs

HazyResearch/ThunderKittens

Tile primitives for speedy kernels

3,674

README badge

Contributors

simarora

6 commits